Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4452 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.9540. Min Act: -0.0000

Data Index: 11952 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1245675 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.4442. Min Act: -0.0000

Data Index: 821070 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1055795 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.3504. Min Act: -0.0000

Data Index: 668753 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.3868. Min Act: -0.0000

Data Index: 624757 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5076. Min Act: -0.0000

Data Index: 479785 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.3947. Min Act: -0.0000

Data Index: 421183 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.4753. Min Act: -0.0000

Data Index: 332780 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.3606. Min Act: -0.0000

Data Index: 46746 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.2895. Min Act: -0.0000

Data Index: 438021 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.0857. Min Act: -0.0000

Data Index: 181137 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.1525. Min Act: -0.0000

Data Index: 46792 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.1600. Min Act: -0.0000

Data Index: 567564 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.1526. Min Act: -0.0000

Data Index: 773536 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.1123. Min Act: -0.0000

Data Index: 887466 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.0574. Min Act: -0.0000

Data Index: 198386 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.2107. Min Act: -0.0000

Data Index: 277770 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1215505 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.9540. Min Range: -1.9540

Max Act: 0.9874. Min Act: -0.0000

Data Index: 858417 (C4 (Web Text))

Max Activating Token Index: 599